[ptx] panosifter problems & questions

[scholnik at radar.nrl.navy.mil]

> hugin uses simple correlation, and will break. the sift features are
> invariant some perspective distortion, but not truely projective invariant.
> While it didn't work as good as with 50° hfov images, I had some success
> with circular fisheye images.

Using a modified version of the "match" program to generate control
points, I've found that the SIFT algorithm is quite good at finding
matching points even in highly-distorted edge regions.  fine-tune in
hugin usually works OK if the starting point is very close to the true
point.

> To transform into a common reference frame, one needs to know the
> transformation, which we are trying to calculate ;)

True, but you can go a long way just using FOV (which should be
roughly known) and perhaps a/b/c.

> > Are
> > there any plans for using rough yaw/pitch/roll/fov/abcde estimates to
> > project the current two images to a common reference frame for
> > control-point picking?
> 
> At some point I might introduce that. but until I get a fisheye or another
> wide angle lens this has low priority for myself. Unfortunately I'm rather
> low on time, and can't implement all the ideas floating around
> immediately. So I concentrate on stuff that is useful for me. Feel free to
> contribute :)

Understandable.  I need to re-learn (modern) C++ before I will feel
comfortable messing around the code.  I've browsed it some and it
reminds me why I'm an engineer and not a CS...

Dan